COORDINATION OF CONNECTION INITIATION SCHEDULING IN A DISTRIBUTED STORAGE NETWORK (DSN)
A dispersed storage network (DSN) include multiple distributed computing systems, each including a DSN memory. A global scheduling module included in a coordination unit identifies a number of the distributed computing systems included in a subset of the distributed computing systems. For each distributed computing system included in the subset, the scheduling module selects a connection time based, at least in part, on the number of distributed computing systems operating in the subset. The connection time selected for a particular distributed computing system specifies a recurring time period to be used by that system for initiating connections with the global coordination unit. The scheduling module issues, to the distributed computing systems, scheduling messages that include information specifying a connection times for particular distributed computing systems.
The present U.S. Utility Patent Application claims priority pursuant to 35 U.S.C. § 120 as a continuation of U.S. Utility application Ser. No. 15/263,564, entitled “COORDINATION OF CONNECTION INITIATION SCHEDULING IN A DISTRIBUTED STORAGE NETWORK (DSN),” filed Sep. 13, 2016, which claims priority pursuant to 35 U.S.C. § 119(e) to U.S. Provisional Application No. 62/222,819, entitled “IDENTIFYING AN ENCODED DATA SLICE FOR REBUILDING,” filed Sep. 24, 2015, both of which are hereby incorporated herein by reference in their entirety and made part of the present U.S. Utility Patent Application for all purposes.
STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENTNot applicable.
INCORPORATION-BY-REFERENCE OF MATERIAL SUBMITTED ON A COMPACT DISCNot applicable.
BACKGROUND OF THE INVENTION Technical Field of the InventionThis invention relates generally to computer networks and more particularly to dispersed storage of data and distributed task processing of data.
Description of Related ArtComputing devices are known to communicate data, process data, and/or store data. Such computing devices range from wireless smart phones, laptops, tablets, personal computers (PC), work stations, and video game devices, to data centers that support millions of web searches, stock trades, or on-line purchases every day. In general, a computing device includes a central processing unit (CPU), a memory system, user input/output interfaces, peripheral device interfaces, and an interconnecting bus structure.
As is further known, a computer may effectively extend its CPU by using “cloud computing” to perform one or more computing functions (e.g., a service, an application, an algorithm, an arithmetic logic function, etc.) on behalf of the computer. Further, for large services, applications, and/or functions, cloud computing may be performed by multiple cloud computing resources in a distributed manner to improve the response time for completion of the service, application, and/or function. For example, Hadoop is an open source software framework that supports distributed applications enabling application execution by thousands of computers.
In addition to cloud computing, a computer may use “cloud storage” as part of its memory system. As is known, cloud storage enables a user, via its computer, to store files, applications, etc., on an Internet storage system. The Internet storage system may include a RAID (redundant array of independent disks) system and/or a dispersed storage system that uses an error correction scheme to encode data for storage.
The DSTN module 22 includes a plurality of distributed storage and/or task (DST) execution units 36 that may be located at geographically different sites (e.g., one in Chicago, one in Milwaukee, etc.). Each of the DST execution units is operable to store dispersed error encoded data and/or to execute, in a distributed manner, one or more tasks on data. The tasks may be a simple function (e.g., a mathematical function, a logic function, an identify function, a find function, a search engine function, a replace function, etc.), a complex function (e.g., compression, human and/or computer language translation, text-to-voice conversion, voice-to-text conversion, etc.), multiple simple and/or complex functions, one or more algorithms, one or more applications, etc.
Each of the user devices 12-14, the DST processing unit 16, the DSTN managing unit 18, and the DST integrity processing unit 20 include a computing core 26 and may be a portable computing device and/or a fixed computing device. A portable computing device may be a social networking device, a gaming device, a cell phone, a smart phone, a personal digital assistant, a digital music player, a digital video player, a laptop computer, a handheld computer, a tablet, a video game controller, and/or any other portable device that includes a computing core. A fixed computing device may be a personal computer (PC), a computer server, a cable set-top box, a satellite receiver, a television set, a printer, a fax machine, home entertainment equipment, a video game console, and/or any type of home or office computing equipment. User device 12 and DST processing unit 16 are configured to include a DST client module 34.
With respect to interfaces, each interface 30, 32, and 33 includes software and/or hardware to support one or more communication links via the network 24 indirectly and/or directly. For example, interface 30 supports a communication link (e.g., wired, wireless, direct, via a LAN, via the network 24, etc.) between user device 14 and the DST processing unit 16. As another example, interface 32 supports communication links (e.g., a wired connection, a wireless connection, a LAN connection, and/or any other type of connection to/from the network 24) between user device 12 and the DSTN module 22 and between the DST processing unit 16 and the DSTN module 22. As yet another example, interface 33 supports a communication link for each of the DSTN managing unit 18 and DST integrity processing unit 20 to the network 24.
The distributed computing system 10 is operable to support dispersed storage (DS) error encoded data storage and retrieval, to support distributed task processing on received data, and/or to support distributed task processing on stored data. In general and with respect to DS error encoded data storage and retrieval, the distributed computing system 10 supports three primary operations: storage management, data storage and retrieval (an example of which will be discussed with reference to
The second primary function (i.e., distributed data storage and retrieval) begins and ends with a user device 12-14. For instance, if a second type of user device 14 has data 40 to store in the DSTN module 22, it sends the data 40 to the DST processing unit 16 via its interface 30. The interface 30 functions to mimic a conventional operating system (OS) file system interface (e.g., network file system (NFS), flash file system (FFS), disk file system (DFS), file transfer protocol (FTP), web-based distributed authoring and versioning (WebDAV), etc.) and/or a block memory interface (e.g., small computer system interface (SCSI), internet small computer system interface (iSCSI), etc.). In addition, the interface 30 may attach a user identification code (ID) to the data 40.
To support storage management, the DSTN managing unit 18 performs DS management services. One such DS management service includes the DSTN managing unit 18 establishing distributed data storage parameters (e.g., vault creation, distributed storage parameters, security parameters, billing information, user profile information, etc.) for a user device 12-14 individually or as part of a group of user devices. For example, the DSTN managing unit 18 coordinates creation of a vault (e.g., a virtual memory block) within memory of the DSTN module 22 for a user device, a group of devices, or for public access and establishes per vault dispersed storage (DS) error encoding parameters for a vault. The DSTN managing unit 18 may facilitate storage of DS error encoding parameters for each vault of a plurality of vaults by updating registry information for the distributed computing system 10. The facilitating includes storing updated registry information in one or more of the DSTN module 22, the user device 12, the DST processing unit 16, and the DST integrity processing unit 20.
The DS error encoding parameters (e.g., or dispersed storage error coding parameters) include data segmenting information (e.g., how many segments data (e.g., a file, a group of files, a data block, etc.) is divided into), segment security information (e.g., per segment encryption, compression, integrity checksum, etc.), error coding information (e.g., pillar width, decode threshold, read threshold, write threshold, etc.), slicing information (e.g., the number of encoded data slices that will be created for each data segment); and slice security information (e.g., per encoded data slice encryption, compression, integrity checksum, etc.).
The DSTN managing unit 18 creates and stores user profile information (e.g., an access control list (ACL)) in local memory and/or within memory of the DSTN module 22. The user profile information includes authentication information, permissions, and/or the security parameters. The security parameters may include encryption/decryption scheme, one or more encryption keys, key generation scheme, and/or data encoding/decoding scheme.
The DSTN managing unit 18 creates billing information for a particular user, a user group, a vault access, public vault access, etc. For instance, the DSTN managing unit 18 tracks the number of times a user accesses a private vault and/or public vaults, which can be used to generate a per-access billing information. In another instance, the DSTN managing unit 18 tracks the amount of data stored and/or retrieved by a user device and/or a user group, which can be used to generate a per-data-amount billing information.
Another DS management service includes the DSTN managing unit 18 performing network operations, network administration, and/or network maintenance. Network operations includes authenticating user data allocation requests (e.g., read and/or write requests), managing creation of vaults, establishing authentication credentials for user devices, adding/deleting components (e.g., user devices, DST execution units, and/or DST processing units) from the distributed computing system 10, and/or establishing authentication credentials for DST execution units 36. Network administration includes monitoring devices and/or units for failures, maintaining vault information, determining device and/or unit activation status, determining device and/or unit loading, and/or determining any other system level operation that affects the performance level of the system 10. Network maintenance includes facilitating replacing, upgrading, repairing, and/or expanding a device and/or unit of the system 10.
To support data storage integrity verification within the distributed computing system 10, the DST integrity processing unit 20 performs rebuilding of ‘bad’ or missing encoded data slices. At a high level, the DST integrity processing unit 20 performs rebuilding by periodically attempting to retrieve/list encoded data slices, and/or slice names of the encoded data slices, from the DSTN module 22. For retrieved encoded slices, they are checked for errors due to data corruption, outdated version, etc. If a slice includes an error, it is flagged as a ‘bad’ slice. For encoded data slices that were not received and/or not listed, they are flagged as missing slices. Bad and/or missing slices are subsequently rebuilt using other retrieved encoded data slices that are deemed to be good slices to produce rebuilt slices. The rebuilt slices are stored in memory of the DSTN module 22. Note that the DST integrity processing unit 20 may be a separate unit as shown, it may be included in the DSTN module 22, it may be included in the DST processing unit 16, and/or distributed among the DST execution units 36.
To support distributed task processing on received data, the distributed computing system 10 has two primary operations: DST (distributed storage and/or task processing) management and DST execution on received data (an example of which will be discussed with reference to
Another DTP management service includes the DSTN managing unit 18 performing DTP network operations, network administration (which is essentially the same as described above), and/or network maintenance (which is essentially the same as described above). Network operations include, but are not limited to, authenticating user task processing requests (e.g., valid request, valid user, etc.), authenticating results and/or partial results, establishing DTP authentication credentials for user devices, adding/deleting components (e.g., user devices, DST execution units, and/or DST processing units) from the distributed computing system, and/or establishing DTP authentication credentials for DST execution units.
To support distributed task processing on stored data, the distributed computing system 10 has two primary operations: DST (distributed storage and/or task) management and DST execution on stored data. With respect to the DST execution on stored data, if the second type of user device 14 has a task request 38 for execution by the DSTN module 22, it sends the task request 38 to the DST processing unit 16 via its interface 30. An example of DST execution on stored data will be discussed in greater detail with reference to
The DSTN interface module 76 functions to mimic a conventional operating system (OS) file system interface (e.g., network file system (NFS), flash file system (FFS), disk file system (DFS), file transfer protocol (FTP), web-based distributed authoring and versioning (WebDAV), etc.) and/or a block memory interface (e.g., small computer system interface (SCSI), internet small computer system interface (iSCSI), etc.). The DSTN interface module 76 and/or the network interface module 70 may function as the interface 30 of the user device 14 of
In an example of operation, the DST client module 34 receives data 92 and one or more tasks 94 to be performed upon the data 92. The data 92 may be of any size and of any content, where, due to the size (e.g., greater than a few Terabytes), the content (e.g., secure data, etc.), and/or task(s) (e.g., MIPS intensive), distributed processing of the task(s) on the data is desired. For example, the data 92 may be one or more digital books, a copy of a company's emails, a large-scale Internet search, a video security file, one or more entertainment video files (e.g., television programs, movies, etc.), data files, and/or any other large amount of data (e.g., greater than a few Terabytes).
Within the DST client module 34, the outbound DST processing section 80 receives the data 92 and the task(s) 94. The outbound DST processing section 80 processes the data 92 to produce slice groupings 96. As an example of such processing, the outbound DST processing section 80 partitions the data 92 into a plurality of data partitions. For each data partition, the outbound DST processing section 80 dispersed storage (DS) error encodes the data partition to produce encoded data slices and groups the encoded data slices into a slice grouping 96. In addition, the outbound DST processing section 80 partitions the task 94 into partial tasks 98, where the number of partial tasks 98 may correspond to the number of slice groupings 96.
The outbound DST processing section 80 then sends, via the network 24, the slice groupings 96 and the partial tasks 98 to the DST execution units 1-n of the DSTN module 22 of
Each DST execution unit performs its partial task 98 upon its slice group 96 to produce partial results 102. For example, DST execution unit #1 performs partial task #1 on slice group #1 to produce a partial result #1, for results. As a more specific example, slice group #1 corresponds to a data partition of a series of digital books and the partial task #1 corresponds to searching for specific phrases, recording where the phrase is found, and establishing a phrase count. In this more specific example, the partial result #1 includes information as to where the phrase was found and includes the phrase count.
Upon completion of generating their respective partial results 102, the DST execution units send, via the network 24, their partial results 102 to the inbound DST processing section 82 of the DST client module 34. The inbound DST processing section 82 processes the received partial results 102 to produce a result 104. Continuing with the specific example of the preceding paragraph, the inbound DST processing section 82 combines the phrase count from each of the DST execution units 36 to produce a total phrase count. In addition, the inbound DST processing section 82 combines the ‘where the phrase was found’ information from each of the DST execution units 36 within their respective data partitions to produce ‘where the phrase was found’ information for the series of digital books.
In another example of operation, the DST client module 34 requests retrieval of stored data within the memory of the DST execution units 36 (e.g., memory of the DSTN module). In this example, the task 94 is retrieve data stored in the memory of the DSTN module. Accordingly, the outbound DST processing section 80 converts the task 94 into a plurality of partial tasks 98 and sends the partial tasks 98 to the respective DST execution units 1-n.
In response to the partial task 98 of retrieving stored data, a DST execution unit 36 identifies the corresponding encoded data slices 100 and retrieves them. For example, DST execution unit #1 receives partial task #1 and retrieves, in response thereto, retrieved slices #1. The DST execution units 36 send their respective retrieved slices 100 to the inbound DST processing section 82 via the network 24.
The inbound DST processing section 82 converts the retrieved slices 100 into data 92. For example, the inbound DST processing section 82 de-groups the retrieved slices 100 to produce encoded slices per data partition. The inbound DST processing section 82 then DS error decodes the encoded slices per data partition to produce data partitions. The inbound DST processing section 82 de-partitions the data partitions to recapture the data 92.
In an example of operation, the data partitioning module 110 partitions data 92 into a plurality of data partitions 120. The number of partitions and the size of the partitions may be selected by the control module 116 via control 160 based on the data 92 (e.g., its size, its content, etc.), a corresponding task 94 to be performed (e.g., simple, complex, single step, multiple steps, etc.), DS encoding parameters (e.g., pillar width, decode threshold, write threshold, segment security parameters, slice security parameters, etc.), capabilities of the DST execution units 36 (e.g., processing resources, availability of processing recourses, etc.), and/or as may be inputted by a user, system administrator, or other operator (human or automated). For example, the data partitioning module 110 partitions the data 92 (e.g., 100 Terabytes) into 100,000 data segments, each being 1 Gigabyte in size. Alternatively, the data partitioning module 110 partitions the data 92 into a plurality of data segments, where some of data segments are of a different size, are of the same size, or a combination thereof.
The DS error encoding module 112 receives the data partitions 120 in a serial manner, a parallel manner, and/or a combination thereof. For each data partition 120, the DS error encoding module 112 DS error encodes the data partition 120 in accordance with control information 160 from the control module 116 to produce encoded data slices 122. The DS error encoding includes segmenting the data partition into data segments, segment security processing (e.g., encryption, compression, watermarking, integrity check (e.g., CRC), etc.), error encoding, slicing, and/or per slice security processing (e.g., encryption, compression, watermarking, integrity check (e.g., CRC), etc.). The control information 160 indicates which steps of the DS error encoding are active for a given data partition and, for active steps, indicates the parameters for the step. For example, the control information 160 indicates that the error encoding is active and includes error encoding parameters (e.g., pillar width, decode threshold, write threshold, read threshold, type of error encoding, etc.).
The grouping selector module 114 groups the encoded slices 122 of a data partition into a set of slice groupings 96. The number of slice groupings corresponds to the number of DST execution units 36 identified for a particular task 94. For example, if five DST execution units 36 are identified for the particular task 94, the grouping selector module groups the encoded slices 122 of a data partition into five slice groupings 96. The grouping selector module 114 outputs the slice groupings 96 to the corresponding DST execution units 36 via the network 24.
The distributed task control module 118 receives the task 94 and converts the task 94 into a set of partial tasks 98. For example, the distributed task control module 118 receives a task to find where in the data (e.g., a series of books) a phrase occurs and a total count of the phrase usage in the data. In this example, the distributed task control module 118 replicates the task 94 for each DST execution unit 36 to produce the partial tasks 98. In another example, the distributed task control module 118 receives a task to find where in the data a first phrase occurs, where in the data a second phrase occurs, and a total count for each phrase usage in the data. In this example, the distributed task control module 118 generates a first set of partial tasks 98 for finding and counting the first phase and a second set of partial tasks for finding and counting the second phrase. The distributed task control module 118 sends respective first and/or second partial tasks 98 to each DST execution unit 36.
The method continues at step 130 where the DST client module determines processing parameters of the data based on the number of DST units selected for distributed task processing. The processing parameters include data partitioning information, DS encoding parameters, and/or slice grouping information. The data partitioning information includes a number of data partitions, size of each data partition, and/or organization of the data partitions (e.g., number of data blocks in a partition, the size of the data blocks, and arrangement of the data blocks). The DS encoding parameters include segmenting information, segment security information, error encoding information (e.g., dispersed storage error encoding function parameters including one or more of pillar width, decode threshold, write threshold, read threshold, generator matrix), slicing information, and/or per slice security information. The slice grouping information includes information regarding how to arrange the encoded data slices into groups for the selected DST units. As a specific example, if the DST client module determines that five DST units are needed to support the task, then it determines that the error encoding parameters include a pillar width of five and a decode threshold of three.
The method continues at step 132 where the DST client module determines task partitioning information (e.g., how to partition the tasks) based on the selected DST units and data processing parameters. The data processing parameters include the processing parameters and DST unit capability information. The DST unit capability information includes the number of DT (distributed task) execution units, execution capabilities of each DT execution unit (e.g., MIPS capabilities, processing resources (e.g., quantity and capability of microprocessors, CPUs, digital signal processors, co-processor, microcontrollers, arithmetic logic circuitry, and/or and the other analog and/or digital processing circuitry), availability of the processing resources, memory information (e.g., type, size, availability, etc.)), and/or any information germane to executing one or more tasks.
The method continues at step 134 where the DST client module processes the data in accordance with the processing parameters to produce slice groupings. The method continues at step 136 where the DST client module partitions the task based on the task partitioning information to produce a set of partial tasks. The method continues at step 138 where the DST client module sends the slice groupings and the corresponding partial tasks to respective DST units.
In an example of operation, the segment processing module 142 receives a data partition 120 from a data partitioning module and receives segmenting information as the control information 160 from the control module 116. The segmenting information indicates how the segment processing module 142 is to segment the data partition 120. For example, the segmenting information indicates how many rows to segment the data based on a decode threshold of an error encoding scheme, indicates how many columns to segment the data into based on a number and size of data blocks within the data partition 120, and indicates how many columns to include in a data segment 152. The segment processing module 142 segments the data 120 into data segments 152 in accordance with the segmenting information.
The segment security processing module 144, when enabled by the control module 116, secures the data segments 152 based on segment security information received as control information 160 from the control module 116. The segment security information includes data compression, encryption, watermarking, integrity check (e.g., cyclic redundancy check (CRC), etc.), and/or any other type of digital security. For example, when the segment security processing module 144 is enabled, it may compress a data segment 152, encrypt the compressed data segment, and generate a CRC value for the encrypted data segment to produce a secure data segment 154. When the segment security processing module 144 is not enabled, it passes the data segments 152 to the error encoding module 146 or is bypassed such that the data segments 152 are provided to the error encoding module 146.
The error encoding module 146 encodes the secure data segments 154 in accordance with error correction encoding parameters received as control information 160 from the control module 116. The error correction encoding parameters (e.g., also referred to as dispersed storage error coding parameters) include identifying an error correction encoding scheme (e.g., forward error correction algorithm, a Reed-Solomon based algorithm, an online coding algorithm, an information dispersal algorithm, etc.), a pillar width, a decode threshold, a read threshold, a write threshold, etc. For example, the error correction encoding parameters identify a specific error correction encoding scheme, specifies a pillar width of five, and specifies a decode threshold of three. From these parameters, the error encoding module 146 encodes a data segment 154 to produce an encoded data segment 156.
The slicing module 148 slices the encoded data segment 156 in accordance with the pillar width of the error correction encoding parameters received as control information 160. For example, if the pillar width is five, the slicing module 148 slices an encoded data segment 156 into a set of five encoded data slices. As such, for a plurality of encoded data segments 156 for a given data partition, the slicing module outputs a plurality of sets of encoded data slices 158.
The per slice security processing module 150, when enabled by the control module 116, secures each encoded data slice 158 based on slice security information received as control information 160 from the control module 116. The slice security information includes data compression, encryption, watermarking, integrity check (e.g., CRC, etc.), and/or any other type of digital security. For example, when the per slice security processing module 150 is enabled, it compresses an encoded data slice 158, encrypts the compressed encoded data slice, and generates a CRC value for the encrypted encoded data slice to produce a secure encoded data slice 122. When the per slice security processing module 150 is not enabled, it passes the encoded data slices 158 or is bypassed such that the encoded data slices 158 are the output of the DS error encoding module 112. Note that the control module 116 may be omitted and each module stores its own parameters.
In this example, the decode threshold of the error encoding scheme is three; as such the number of rows to divide the data partition into is three. The number of columns for each row is set to 15, which is based on the number and size of data blocks. The data blocks of the data partition are arranged in rows and columns in a sequential order (i.e., the first row includes the first 15 data blocks; the second row includes the second 15 data blocks; and the third row includes the last 15 data blocks).
With the data blocks arranged into the desired sequential order, they are divided into data segments based on the segmenting information. In this example, the data partition is divided into 8 data segments; the first 7 include 2 columns of three rows and the last includes 1 column of three rows. Note that the first row of the 8 data segments is in sequential order of the first 15 data blocks; the second row of the 8 data segments in sequential order of the second 15 data blocks; and the third row of the 8 data segments in sequential order of the last 15 data blocks. Note that the number of data blocks, the grouping of the data blocks into segments, and size of the data blocks may vary to accommodate the desired distributed task processing function.
In operation, an error encoding module 146 and a slicing module 148 convert each data segment into a set of encoded data slices in accordance with error correction encoding parameters as control information 160. More specifically, when the error correction encoding parameters indicate a unity matrix Reed-Solomon based encoding algorithm, 5 pillars, and decode threshold of 3, the first three encoded data slices of the set of encoded data slices for a data segment are substantially similar to the corresponding word of the data segment. For instance, when the unity matrix Reed-Solomon based encoding algorithm is applied to data segment 1, the content of the first encoded data slice (DS1_d1&2) of the first set of encoded data slices (e.g., corresponding to data segment 1) is substantially similar to content of the first word (e.g., d1 & d2); the content of the second encoded data slice (DS1_d16&17) of the first set of encoded data slices is substantially similar to content of the second word (e.g., d16 & d17); and the content of the third encoded data slice (DS1_d31&32) of the first set of encoded data slices is substantially similar to content of the third word (e.g., d31 & d32).
The content of the fourth and fifth encoded data slices (e.g., ES1_1 and ES1_2) of the first set of encoded data slices include error correction data based on the first-third words of the first data segment. With such an encoding and slicing scheme, retrieving any three of the five encoded data slices allows the data segment to be accurately reconstructed.
The encoding and slices of data segments 2-7 yield sets of encoded data slices similar to the set of encoded data slices of data segment 1. For instance, the content of the first encoded data slice (DS2_d3&4) of the second set of encoded data slices (e.g., corresponding to data segment 2) is substantially similar to content of the first word (e.g., d3 & d4); the content of the second encoded data slice (DS2_d18&19) of the second set of encoded data slices is substantially similar to content of the second word (e.g., d18 & d19); and the content of the third encoded data slice (DS2_d33&34) of the second set of encoded data slices is substantially similar to content of the third word (e.g., d33 & d34). The content of the fourth and fifth encoded data slices (e.g., ES1_1 and ES1_2) of the second set of encoded data slices includes error correction data based on the first-third words of the second data segment.
The grouping selection module 114 also creates a second slice grouping for a DST execution unit #2, which includes second encoded slices of each of the sets of encoded slices. As such, the second DST execution unit receives encoded data slices corresponding to data blocks 16-30. The grouping selection module 114 further creates a third slice grouping for DST execution unit #3, which includes third encoded slices of each of the sets of encoded slices. As such, the third DST execution unit receives encoded data slices corresponding to data blocks 31-45.
The grouping selection module 114 creates a fourth slice grouping for DST execution unit #4, which includes fourth encoded slices of each of the sets of encoded slices. As such, the fourth DST execution unit receives encoded data slices corresponding to first error encoding information (e.g., encoded data slices of error coding (EC) data). The grouping selection module 114 further creates a fifth slice grouping for DST execution unit #5, which includes fifth encoded slices of each of the sets of encoded slices. As such, the fifth DST execution unit receives encoded data slices corresponding to second error encoding information.
For example, the slice groupings of data partition #1 is sent to the DST execution units such that the first DST execution receives first encoded data slices of each of the sets of encoded data slices, which corresponds to a first continuous data chunk of the first data partition (e.g., refer to
For the second data partition, the slice groupings may be sent to the DST execution units in a different order than it was done for the first data partition. For instance, the first slice grouping of the second data partition (e.g., slice group 2_1) is sent to the second DST execution unit; the second slice grouping of the second data partition (e.g., slice group 2_2) is sent to the third DST execution unit; the third slice grouping of the second data partition (e.g., slice group 2_3) is sent to the fourth DST execution unit; the fourth slice grouping of the second data partition (e.g., slice group 2_4, which includes first error coding information) is sent to the fifth DST execution unit; and the fifth slice grouping of the second data partition (e.g., slice group 2_5, which includes second error coding information) is sent to the first DST execution unit.
The pattern of sending the slice groupings to the set of DST execution units may vary in a predicted pattern, a random pattern, and/or a combination thereof from data partition to data partition. In addition, from data partition to data partition, the set of DST execution units may change. For example, for the first data partition, DST execution units 1-5 may be used; for the second data partition, DST execution units 6-10 may be used; for the third data partition, DST execution units 3-7 may be used; etc. As is also shown, the task is divided into partial tasks that are sent to the DST execution units in conjunction with the slice groupings of the data partitions.
In an example of storing a slice group, the DST execution module receives a slice grouping 96 (e.g., slice group #1) via interface 169. The slice grouping 96 includes, per partition, encoded data slices of contiguous data or encoded data slices of error coding (EC) data. For slice group #1, the DST execution module receives encoded data slices of contiguous data for partitions #1 and #x (and potentially others between 3 and x) and receives encoded data slices of EC data for partitions #2 and #3 (and potentially others between 3 and x). Examples of encoded data slices of contiguous data and encoded data slices of error coding (EC) data are discussed with reference to
The controller 86 (e.g., a processing module, a CPU, etc.) generates the memory control information 174 based on a partial task(s) 98 and distributed computing information (e.g., user information (e.g., user ID, distributed computing permissions, data access permission, etc.), vault information (e.g., virtual memory assigned to user, user group, temporary storage for task processing, etc.), task validation information, etc.). For example, the controller 86 interprets the partial task(s) 98 in light of the distributed computing information to determine whether a requestor is authorized to perform the task 98, is authorized to access the data, and/or is authorized to perform the task on this particular data. When the requestor is authorized, the controller 86 determines, based on the task 98 and/or another input, whether the encoded data slices of the slice grouping 96 are to be temporarily stored or permanently stored. Based on the foregoing, the controller 86 generates the memory control information 174 to write the encoded data slices of the slice grouping 96 into the memory 88 and to indicate whether the slice grouping 96 is permanently stored or temporarily stored.
With the slice grouping 96 stored in the memory 88, the controller 86 facilitates execution of the partial task(s) 98. In an example, the controller 86 interprets the partial task 98 in light of the capabilities of the DT execution module(s) 90. The capabilities include one or more of MIPS capabilities, processing resources (e.g., quantity and capability of microprocessors, CPUs, digital signal processors, co-processor, microcontrollers, arithmetic logic circuitry, and/or any other analog and/or digital processing circuitry), availability of the processing resources, etc. If the controller 86 determines that the DT execution module(s) 90 have sufficient capabilities, it generates task control information 176.
The task control information 176 may be a generic instruction (e.g., perform the task on the stored slice grouping) or a series of operational codes. In the former instance, the DT execution module 90 includes a co-processor function specifically configured (fixed or programmed) to perform the desired task 98. In the latter instance, the DT execution module 90 includes a general processor topology where the controller stores an algorithm corresponding to the particular task 98. In this instance, the controller 86 provides the operational codes (e.g., assembly language, source code of a programming language, object code, etc.) of the algorithm to the DT execution module 90 for execution.
Depending on the nature of the task 98, the DT execution module 90 may generate intermediate partial results 102 that are stored in the memory 88 or in a cache memory (not shown) within the DT execution module 90. In either case, when the DT execution module 90 completes execution of the partial task 98, it outputs one or more partial results 102. The partial results 102 may also be stored in memory 88.
If, when the controller 86 is interpreting whether capabilities of the DT execution module(s) 90 can support the partial task 98, the controller 86 determines that the DT execution module(s) 90 cannot adequately support the task 98 (e.g., does not have the right resources, does not have sufficient available resources, available resources would be too slow, etc.), it then determines whether the partial task 98 should be fully offloaded or partially offloaded.
If the controller 86 determines that the partial task 98 should be fully offloaded, it generates DST control information 178 and provides it to the DST client module 34. The DST control information 178 includes the partial task 98, memory storage information regarding the slice grouping 96, and distribution instructions. The distribution instructions instruct the DST client module 34 to divide the partial task 98 into sub-partial tasks 172, to divide the slice grouping 96 into sub-slice groupings 170, and identify other DST execution units. The DST client module 34 functions in a similar manner as the DST client module 34 of
The DST client module 34 receives DST feedback 168 (e.g., sub-partial results), via the interface 169, from the DST execution units to which the task was offloaded. The DST client module 34 provides the sub-partial results to the DST execution unit, which processes the sub-partial results to produce the partial result(s) 102.
If the controller 86 determines that the partial task 98 should be partially offloaded, it determines what portion of the task 98 and/or slice grouping 96 should be processed locally and what should be offloaded. For the portion that is being locally processed, the controller 86 generates task control information 176 as previously discussed. For the portion that is being offloaded, the controller 86 generates DST control information 178 as previously discussed.
When the DST client module 34 receives DST feedback 168 (e.g., sub-partial results) from the DST executions units to which a portion of the task was offloaded, it provides the sub-partial results to the DT execution module 90. The DT execution module 90 processes the sub-partial results with the sub-partial results it created to produce the partial result(s) 102.
The memory 88 may be further utilized to retrieve one or more of stored slices 100, stored results 104, partial results 102 when the DT execution module 90 stores partial results 102 and/or results 104 in the memory 88. For example, when the partial task 98 includes a retrieval request, the controller 86 outputs the memory control 174 to the memory 88 to facilitate retrieval of slices 100 and/or results 104.
Once the encoded slices are stored, the controller 86 provides task control information 176 to a distributed task (DT) execution module 90. As a first step of executing the task in accordance with the task control information 176, the DT execution module 90 retrieves the encoded slices from memory 88. The DT execution module 90 then reconstructs contiguous data blocks of a data partition. As shown for this example, reconstructed contiguous data blocks of data partition 1 include data blocks 1-15 (e.g., d1-d15).
With the contiguous data blocks reconstructed, the DT execution module 90 performs the task on the reconstructed contiguous data blocks. For example, the task may be to search the reconstructed contiguous data blocks for a particular word or phrase, identify where in the reconstructed contiguous data blocks the particular word or phrase occurred, and/or count the occurrences of the particular word or phrase on the reconstructed contiguous data blocks. The DST execution unit continues in a similar manner for the encoded data slices of other partitions in slice grouping 1. Note that with using the unity matrix error encoding scheme previously discussed, if the encoded data slices of contiguous data are uncorrupted, the decoding of them is a relatively straightforward process of extracting the data.
If, however, an encoded data slice of contiguous data is corrupted (or missing), it can be rebuilt by accessing other DST execution units that are storing the other encoded data slices of the set of encoded data slices of the corrupted encoded data slice. In this instance, the DST execution unit having the corrupted encoded data slices retrieves at least three encoded data slices (of contiguous data and of error coding data) in the set from the other DST execution units (recall for this example, the pillar width is 5 and the decode threshold is 3). The DST execution unit decodes the retrieved data slices using the DS error encoding parameters to recapture the corresponding data segment. The DST execution unit then re-encodes the data segment using the DS error encoding parameters to rebuild the corrupted encoded data slice. Once the encoded data slice is rebuilt, the DST execution unit functions as previously described.
In an example of operation, the DST execution units have completed execution of corresponding partial tasks on the corresponding slice groupings to produce partial results 102. The inbound DST processing section 82 receives the partial results 102 via the distributed task control module 188. The inbound DST processing section 82 then processes the partial results 102 to produce a final result, or results 104. For example, if the task was to find a specific word or phrase within data, the partial results 102 indicate where in each of the prescribed portions of the data the corresponding DST execution units found the specific word or phrase. The distributed task control module 188 combines the individual partial results 102 for the corresponding portions of the data into a final result 104 for the data as a whole.
In another example of operation, the inbound DST processing section 82 is retrieving stored data from the DST execution units (i.e., the DSTN module). In this example, the DST execution units output encoded data slices 100 corresponding to the data retrieval requests. The de-grouping module 180 receives retrieved slices 100 and de-groups them to produce encoded data slices per data partition 122. The DS error decoding module 182 decodes, in accordance with DS error encoding parameters, the encoded data slices per data partition 122 to produce data partitions 120.
The data de-partitioning module 184 combines the data partitions 120 into the data 92. The control module 186 controls the conversion of retrieved slices 100 into the data 92 using control signals 190 to each of the modules. For instance, the control module 186 provides de-grouping information to the de-grouping module 180, provides the DS error encoding parameters to the DS error decoding module 182, and provides de-partitioning information to the data de-partitioning module 184.
The method continues at step 198 where the DST client module determines result processing information based on the task. For example, if the task were to identify a particular word or phrase within the data, the result processing information would indicate to aggregate the partial results for the corresponding portions of the data to produce the final result. As another example, if the task were to count the occurrences of a particular word or phrase within the data, results of processing the information would indicate to add the partial results to produce the final results. The method continues at step 200 where the DST client module processes the partial results in accordance with the result processing information to produce the final result or results.
As shown, DST execution unit #1 provides a first slice grouping, which includes the first encoded slices of each of the sets of encoded slices (e.g., encoded data slices of contiguous data of data blocks 1-15); DST execution unit #2 provides a second slice grouping, which includes the second encoded slices of each of the sets of encoded slices (e.g., encoded data slices of contiguous data of data blocks 16-30); DST execution unit #3 provides a third slice grouping, which includes the third encoded slices of each of the sets of encoded slices (e.g., encoded data slices of contiguous data of data blocks 31-45); DST execution unit #4 provides a fourth slice grouping, which includes the fourth encoded slices of each of the sets of encoded slices (e.g., first encoded data slices of error coding (EC) data); and DST execution unit #5 provides a fifth slice grouping, which includes the fifth encoded slices of each of the sets of encoded slices (e.g., first encoded data slices of error coding (EC) data).
The de-grouping module de-groups the slice groupings (e.g., received slices 100) using a de-grouping selector 180 controlled by a control signal 190 as shown in the example to produce a plurality of sets of encoded data slices (e.g., retrieved slices for a partition into sets of slices 122). Each set corresponding to a data segment of the data partition.
In an example of operation, the inverse per slice security processing module 202, when enabled by the control module 186, unsecures each encoded data slice 122 based on slice de-security information received as control information 190 (e.g., the compliment of the slice security information discussed with reference to
The de-slicing module 204 de-slices the sliced encoded data 158 into encoded data segments 156 in accordance with a pillar width of the error correction encoding parameters received as control information 190 from the control module 186. For example, if the pillar width is five, the de-slicing module 204 de-slices a set of five encoded data slices into an encoded data segment 156. The error decoding module 206 decodes the encoded data segments 156 in accordance with error correction decoding parameters received as control information 190 from the control module 186 to produce secure data segments 154. The error correction decoding parameters include identifying an error correction encoding scheme (e.g., forward error correction algorithm, a Reed-Solomon based algorithm, an information dispersal algorithm, etc.), a pillar width, a decode threshold, a read threshold, a write threshold, etc. For example, the error correction decoding parameters identify a specific error correction encoding scheme, specify a pillar width of five, and specify a decode threshold of three.
The inverse segment security processing module 208, when enabled by the control module 186, unsecures the secured data segments 154 based on segment security information received as control information 190 from the control module 186. The segment security information includes data decompression, decryption, de-watermarking, integrity check (e.g., CRC, etc.) verification, and/or any other type of digital security. For example, when the inverse segment security processing module 208 is enabled, it verifies integrity information (e.g., a CRC value) of each secure data segment 154, it decrypts each verified secured data segment, and decompresses each decrypted secure data segment to produce a data segment 152. When the inverse segment security processing module 208 is not enabled, it passes the decoded data segment 154 as the data segment 152 or is bypassed.
The de-segment processing module 210 receives the data segments 152 and receives de-segmenting information as control information 190 from the control module 186. The de-segmenting information indicates how the de-segment processing module 210 is to de-segment the data segments 152 into a data partition 120. For example, the de-segmenting information indicates how the rows and columns of data segments are to be rearranged to yield the data partition 120.
An error decoding module 206 decodes the encoded data 156 of each data segment in accordance with the error correction decoding parameters of control information 190 to produce secured segments 154. In this example, data segment 1 includes 3 rows with each row being treated as one word for encoding. As such, data segment 1 includes three words: word 1 including data blocks dl and d2, word 2 including data blocks d16 and d17, and word 3 including data blocks d31 and d32. Each of data segments 2-7 includes three words where each word includes two data blocks. Data segment 8 includes three words where each word includes a single data block (e.g., d15, d30, and d45).
The de-segmenting module 210 converts the rows and columns of data blocks into the data partition 120. Note that each data block may be of the same size as other data blocks or of a different size. In addition, the size of each data block may be a few bytes to megabytes of data.
In an example of data storage, the DST client module 34 has data 92 that it desires to store in the DSTN module. The data 92 may be a file (e.g., video, audio, text, graphics, etc.), a data object, a data block, an update to a file, an update to a data block, etc. In this instance, the outbound DST processing module 80 converts the data 92 into encoded data slices 216 as will be further described with reference to
In an example of data retrieval, the DST client module 34 issues a retrieve request to the DST execution units for the desired data 92. The retrieve request may address each DST executions units storing encoded data slices of the desired data, address a decode threshold number of DST execution units, address a read threshold number of DST execution units, or address some other number of DST execution units. In response to the request, each addressed DST execution unit retrieves its encoded data slices 100 of the desired data and sends them to the inbound DST processing section 82, via the network 24.
When, for each data segment, the inbound DST processing section 82 receives at least a decode threshold number of encoded data slices 100, it converts the encoded data slices 100 into a data segment. The inbound DST processing section 82 aggregates the data segments to produce the retrieved data 92.
In an example of operation, the data partitioning module 110 is by-passed such that data 92 is provided directly to the DS error encoding module 112. The control module 116 coordinates the by-passing of the data partitioning module 110 by outputting a bypass 220 message to the data partitioning module 110.
The DS error encoding module 112 receives the data 92 in a serial manner, a parallel manner, and/or a combination thereof. The DS error encoding module 112 DS error encodes the data in accordance with control information 160 from the control module 116 to produce encoded data slices 218. The DS error encoding includes segmenting the data 92 into data segments, segment security processing (e.g., encryption, compression, watermarking, integrity check (e.g., CRC, etc.)), error encoding, slicing, and/or per slice security processing (e.g., encryption, compression, watermarking, integrity check (e.g., CRC, etc.)). The control information 160 indicates which steps of the DS error encoding are active for the data 92 and, for active steps, indicates the parameters for the step. For example, the control information 160 indicates that the error encoding is active and includes error encoding parameters (e.g., pillar width, decode threshold, write threshold, read threshold, type of error encoding, etc.).
The grouping selector module 114 groups the encoded slices 218 of the data segments into pillars of slices 216. The number of pillars corresponds to the pillar width of the DS error encoding parameters. In this example, the distributed task control module 118 facilitates the storage request.
In an example of operation, the segment processing module 142 receives data 92 and receives segmenting information as control information 160 from the control module 116. The segmenting information indicates how the segment processing module is to segment the data. For example, the segmenting information indicates the size of each data segment. The segment processing module 142 segments the data 92 into data segments 152 in accordance with the segmenting information.
The segment security processing module 144, when enabled by the control module 116, secures the data segments 152 based on segment security information received as control information 160 from the control module 116. The segment security information includes data compression, encryption, watermarking, integrity check (e.g., CRC, etc.), and/or any other type of digital security. For example, when the segment security processing module 144 is enabled, it compresses a data segment 152, encrypts the compressed data segment, and generates a CRC value for the encrypted data segment to produce a secure data segment. When the segment security processing module 144 is not enabled, it passes the data segments 152 to the error encoding module 146 or is bypassed such that the data segments 152 are provided to the error encoding module 146.
The error encoding module 146 encodes the secure data segments in accordance with error correction encoding parameters received as control information 160 from the control module 116. The error correction encoding parameters include identifying an error correction encoding scheme (e.g., forward error correction algorithm, a Reed-Solomon based algorithm, an information dispersal algorithm, etc.), a pillar width, a decode threshold, a read threshold, a write threshold, etc. For example, the error correction encoding parameters identify a specific error correction encoding scheme, specifies a pillar width of five, and specifies a decode threshold of three. From these parameters, the error encoding module 146 encodes a data segment to produce an encoded data segment.
The slicing module 148 slices the encoded data segment in accordance with a pillar width of the error correction encoding parameters. For example, if the pillar width is five, the slicing module slices an encoded data segment into a set of five encoded data slices. As such, for a plurality of data segments, the slicing module 148 outputs a plurality of sets of encoded data slices as shown within encoding and slicing function 222 as described.
The per slice security processing module 150, when enabled by the control module 116, secures each encoded data slice based on slice security information received as control information 160 from the control module 116. The slice security information includes data compression, encryption, watermarking, integrity check (e.g., CRC, etc.), and/or any other type of digital security. For example, when the per slice security processing module 150 is enabled, it may compress an encoded data slice, encrypt the compressed encoded data slice, and generate a CRC value for the encrypted encoded data slice to produce a secure encoded data slice tweaking. When the per slice security processing module 150 is not enabled, it passes the encoded data slices or is bypassed such that the encoded data slices 218 are the output of the DS error encoding module 112.
The grouping selection module takes the first encoded data slice of each of the sets and forms a first pillar, which may be sent to the first DST execution unit. Similarly, the grouping selection module creates the second pillar from the second slices of the sets; the third pillar from the third slices of the sets; the fourth pillar from the fourth slices of the sets; and the fifth pillar from the fifth slices of the set.
In an example of storing a pillar of slices 216, the DST execution unit receives, via interface 169, a pillar of slices 216 (e.g., pillar #1 slices). The memory 88 stores the encoded data slices 216 of the pillar of slices in accordance with memory control information 174 it receives from the controller 86. The controller 86 (e.g., a processing module, a CPU, etc.) generates the memory control information 174 based on distributed storage information (e.g., user information (e.g., user ID, distributed storage permissions, data access permission, etc.), vault information (e.g., virtual memory assigned to user, user group, etc.), etc.). Similarly, when retrieving slices, the DST execution unit receives, via interface 169, a slice retrieval request. The memory 88 retrieves the slice in accordance with memory control information 174 it receives from the controller 86. The memory 88 outputs the slice 100, via the interface 169, to a requesting entity.
In an example of operation, the inbound DST processing section 82 is retrieving stored data 92 from the DST execution units (i.e., the DSTN module). In this example, the DST execution units output encoded data slices corresponding to data retrieval requests from the distributed task control module 188. The de-grouping module 180 receives pillars of slices 100 and de-groups them in accordance with control information 190 from the control module 186 to produce sets of encoded data slices 218. The DS error decoding module 182 decodes, in accordance with the DS error encoding parameters received as control information 190 from the control module 186, each set of encoded data slices 218 to produce data segments, which are aggregated into retrieved data 92. The data de-partitioning module 184 is by-passed in this operational mode via a bypass signal 226 of control information 190 from the control module 186.
In an example of operation, the inverse per slice security processing module 202, when enabled by the control module 186 via control information 190, unsecures each encoded data slice 218 based on slice de-security information (e.g., the compliment of the slice security information discussed with reference to
The de-slicing module 204 de-slices the sliced encoded data into encoded data segments in accordance with a pillar width of the error correction encoding parameters received as control information 190 from a control module 186. For example, if the pillar width is five, the de-slicing module de-slices a set of five encoded data slices into an encoded data segment. Alternatively, the encoded data segment may include just three encoded data slices (e.g., when the decode threshold is 3).
The error decoding module 206 decodes the encoded data segments in accordance with error correction decoding parameters received as control information 190 from the control module 186 to produce secure data segments. The error correction decoding parameters include identifying an error correction encoding scheme (e.g., forward error correction algorithm, a Reed-Solomon based algorithm, an information dispersal algorithm, etc.), a pillar width, a decode threshold, a read threshold, a write threshold, etc. For example, the error correction decoding parameters identify a specific error correction encoding scheme, specify a pillar width of five, and specify a decode threshold of three.
The inverse segment security processing module 208, when enabled by the control module 186, unsecures the secured data segments based on segment security information received as control information 190 from the control module 186. The segment security information includes data decompression, decryption, de-watermarking, integrity check (e.g., CRC, etc.) verification, and/or any other type of digital security. For example, when the inverse segment security processing module is enabled, it verifies integrity information (e.g., a CRC value) of each secure data segment, it decrypts each verified secured data segment, and decompresses each decrypted secure data segment to produce a data segment 152. When the inverse segment security processing module 208 is not enabled, it passes the decoded data segment 152 as the data segment or is bypassed. The de-segmenting processing module 210 aggregates the data segments 152 into the data 92 in accordance with control information 190 from the control module 186.
In this example, the DSTN module stores, in the memory of the DST execution units, a plurality of DS (dispersed storage) encoded data (e.g., 1 through n, where n is an integer greater than or equal to two) and stores a plurality of DS encoded task codes (e.g., 1 through k, where k is an integer greater than or equal to two). The DS encoded data may be encoded in accordance with one or more examples described with reference to
The tasks that are encoded into the DS encoded task code may be a simple function (e.g., a mathematical function, a logic function, an identify function, a find function, a search engine function, a replace function, etc.), a complex function (e.g., compression, human and/or computer language translation, text-to-voice conversion, voice-to-text conversion, etc.), multiple simple and/or complex functions, one or more algorithms, one or more applications, etc. The tasks may be encoded into the DS encoded task code in accordance with one or more examples described with reference to
In an example of operation, a DST client module of a user device or of a DST processing unit issues a DST request to the DSTN module. The DST request may include a request to retrieve stored data, or a portion thereof, may include a request to store data that is included with the DST request, may include a request to perform one or more tasks on stored data, may include a request to perform one or more tasks on data included with the DST request, etc. In the cases where the DST request includes a request to store data or to retrieve data, the client module and/or the DSTN module processes the request as previously discussed with reference to one or more of
In the case where the DST request includes a request to perform one or more tasks on stored data, the DST client module and/or the DSTN module processes the DST request as will be described with reference to one or more of
As shown, the list of data 234 and the list of tasks 236 are each smaller in number of entries for the first DST client module than the corresponding lists of the second DST client module. This may occur because the user device associated with the first DST client module has fewer privileges in the distributed computing system than the device associated with the second DST client module. Alternatively, this may occur because the user device associated with the first DST client module serves fewer users than the device associated with the second DST client module and is restricted by the distributed computing system accordingly. As yet another alternative, this may occur through no restraints by the distributed computing system, it just occurred because the operator of the user device associated with the first DST client module has selected fewer data and/or fewer tasks than the operator of the device associated with the second DST client module.
In an example of operation, the first DST client module selects one or more data entries 238 and one or more tasks 240 from its respective lists (e.g., selected data ID and selected task ID). The first DST client module sends its selections to a task distribution module 232. The task distribution module 232 may be within a stand-alone device of the distributed computing system, may be within the user device that contains the first DST client module, or may be within the DSTN module 22.
Regardless of the task distribution module's location, it generates DST allocation information 242 from the selected task ID 240 and the selected data ID 238. The DST allocation information 242 includes data partitioning information, task execution information, and/or intermediate result information. The task distribution module 232 sends the DST allocation information 242 to the DSTN module 22. Note that one or more examples of the DST allocation information will be discussed with reference to one or more of
The DSTN module 22 interprets the DST allocation information 242 to identify the stored DS encoded data (e.g., DS error encoded data 2) and to identify the stored DS error encoded task code (e.g., DS error encoded task code 1). In addition, the DSTN module 22 interprets the DST allocation information 242 to determine how the data is to be partitioned and how the task is to be partitioned. The DSTN module 22 also determines whether the selected DS error encoded data 238 needs to be converted from pillar grouping to slice grouping. If so, the DSTN module 22 converts the selected DS error encoded data into slice groupings and stores the slice grouping DS error encoded data by overwriting the pillar grouping DS error encoded data or by storing it in a different location in the memory of the DSTN module 22 (i.e., does not overwrite the pillar grouping DS encoded data).
The DSTN module 22 partitions the data and the task as indicated in the DST allocation information 242 and sends the portions to selected DST execution units of the DSTN module 22. Each of the selected DST execution units performs its partial task(s) on its slice groupings to produce partial results. The DSTN module 22 collects the partial results from the selected DST execution units and provides them, as result information 244, to the task distribution module. The result information 244 may be the collected partial results, one or more final results as produced by the DSTN module 22 from processing the partial results in accordance with the DST allocation information 242, or one or more intermediate results as produced by the DSTN module 22 from processing the partial results in accordance with the DST allocation information 242.
The task distribution module 232 receives the result information 244 and provides one or more final results 104 therefrom to the first DST client module. The final result(s) 104 may be result information 244 or a result(s) of the task distribution module's processing of the result information 244.
In concurrence with processing the selected task of the first DST client module, the distributed computing system may process the selected task(s) of the second DST client module on the selected data(s) of the second DST client module. Alternatively, the distributed computing system may process the second DST client module's request subsequent to, or preceding, that of the first DST client module. Regardless of the ordering and/or parallel processing of the DST client module requests, the second DST client module provides its selected data 238 and selected task 240 to a task distribution module 232. If the task distribution module 232 is a separate device of the distributed computing system or within the DSTN module, the task distribution modules 232 coupled to the first and second DST client modules may be the same module. The task distribution module 232 processes the request of the second DST client module in a similar manner as it processed the request of the first DST client module.
The data storage information table 248 includes a data identification (ID) field 260, a data size field 262, an addressing information field 264, distributed storage (DS) information 266, and may further include other information regarding the data, how it is stored, and/or how it can be processed. For example, DS encoded data #1 has a data ID of 1, a data size of AA (e.g., a byte size of a few Terabytes or more), addressing information of Addr_1_AA, and DS parameters of 3/5; SEG_1; and SLC_1. In this example, the addressing information may be a virtual address corresponding to the virtual address of the first storage word (e.g., one or more bytes) of the data and information on how to calculate the other addresses, may be a range of virtual addresses for the storage words of the data, physical addresses of the first storage word or the storage words of the data, may be a list of slice names of the encoded data slices of the data, etc. The DS parameters may include identity of an error encoding scheme, decode threshold/pillar width (e.g., 3/5 for the first data entry), segment security information (e.g., SEG_1), per slice security information (e.g., SLC_1), and/or any other information regarding how the data was encoded into data slices.
The task storage information table 250 includes a task identification (ID) field 268, a task size field 270, an addressing information field 272, distributed storage (DS) information 274, and may further include other information regarding the task, how it is stored, and/or how it can be used to process data. For example, DS encoded task #2 has a task ID of 2, a task size of XY, addressing information of Addr_2_XY, and DS parameters of 3/5; SEG_2; and SLC_2. In this example, the addressing information may be a virtual address corresponding to the virtual address of the first storage word (e.g., one or more bytes) of the task and information on how to calculate the other addresses, may be a range of virtual addresses for the storage words of the task, physical addresses of the first storage word or the storage words of the task, may be a list of slices names of the encoded slices of the task code, etc. The DS parameters may include identity of an error encoding scheme, decode threshold/pillar width (e.g., 3/5 for the first data entry), segment security information (e.g., SEG_2), per slice security information (e.g., SLC_2), and/or any other information regarding how the task was encoded into encoded task slices. Note that the segment and/or the per-slice security information include a type of encryption (if enabled), a type of compression (if enabled), watermarking information (if enabled), and/or an integrity check scheme (if enabled).
The task ⇔ sub-task mapping information table 246 includes a task field 256 and a sub-task field 258. The task field 256 identifies a task stored in the memory of a distributed storage and task network (DSTN) module and the corresponding sub-task fields 258 indicates whether the task includes sub-tasks and, if so, how many and if any of the sub-tasks are ordered. In this example, the task ⇔ sub-task mapping information table 246 includes an entry for each task stored in memory of the DSTN module (e.g., task 1 through task k). In particular, this example indicates that task 1 includes 7 sub-tasks; task 2 does not include sub-tasks, and task k includes r number of sub-tasks (where r is an integer greater than or equal to two).
The DT execution module table 252 includes a DST execution unit ID field 276, a DT execution module ID field 278, and a DT execution module capabilities field 280. The DST execution unit ID field 276 includes the identity of DST units in the DSTN module. The DT execution module ID field 278 includes the identity of each DT execution unit in each DST unit. For example, DST unit 1 includes three DT executions modules (e.g., 1_1, 1_2, and 1_3). The DT execution capabilities field 280 includes identity of the capabilities of the corresponding DT execution unit. For example, DT execution module 1_1 includes capabilities X, where X includes one or more of MIPS capabilities, processing resources (e.g., quantity and capability of microprocessors, CPUs, digital signal processors, co-processor, microcontrollers, arithmetic logic circuitry, and/or any other analog and/or digital processing circuitry), availability of the processing resources, memory information (e.g., type, size, availability, etc.), and/or any information germane to executing one or more tasks.
From these tables, the task distribution module 232 generates the DST allocation information 242 to indicate where the data is stored, how to partition the data, where the task is stored, how to partition the task, which DT execution units should perform which partial task on which data partitions, where and how intermediate results are to be stored, etc. If multiple tasks are being performed on the same data or different data, the task distribution module factors such information into its generation of the DST allocation information.
In this example, task 1 includes 7 sub-tasks: task 1_1—identify non-words (non-ordered); task 1_2—identify unique words (non-ordered); task 1_3—translate (non-ordered); task 1_4—translate back (ordered after task 1_3); task 1_5—compare to ID errors (ordered after task 1-4); task 1_6—determine non-word translation errors (ordered after task 1_5 and 1_1); and task 1_7—determine correct translations (ordered after 1_5 and 1_2). The sub-task further indicates whether they are an ordered task (i.e., are dependent on the outcome of another task) or non-order (i.e., are independent of the outcome of another task). Task 2 does not include sub-tasks and task 3 includes two sub-tasks: task 3_1 translate; and task 3_2 find specific word or phrase in translated data.
In general, the three tasks collectively are selected to analyze data for translation accuracies, translation errors, translation anomalies, occurrence of specific words or phrases in the data, and occurrence of specific words or phrases on the translated data. Graphically, the data 92 is translated 306 into translated data 282; is analyzed for specific words and/or phrases 300 to produce a list of specific words and/or phrases 286; is analyzed for non-words 302 (e.g., not in a reference dictionary) to produce a list of non-words 290; and is analyzed for unique words 316 included in the data 92 (i.e., how many different words are included in the data) to produce a list of unique words 298. Each of these tasks is independent of each other and can therefore be processed in parallel if desired.
The translated data 282 is analyzed (e.g., sub-task 3 2) for specific translated words and/or phrases 304 to produce a list of specific translated words and/or phrases 288. The translated data 282 is translated back 308 (e.g., sub-task 1_4) into the language of the original data to produce re-translated data 284. These two tasks are dependent on the translate task (e.g., task 1_3) and thus must be ordered after the translation task, which may be in a pipelined ordering or a serial ordering. The re-translated data 284 is then compared 310 with the original data 92 to find words and/or phrases that did not translate (one way and/or the other) properly to produce a list of incorrectly translated words 294. As such, the comparing task (e.g., sub-task 1_5) 310 is ordered after the translation 306 and re-translation tasks 308 (e.g., sub-tasks 1_3 and 1_4).
The list of words incorrectly translated 294 is compared 312 to the list of non-words 290 to identify words that were not properly translated because the words are non-words to produce a list of errors due to non-words 292. In addition, the list of words incorrectly translated 294 is compared 314 to the list of unique words 298 to identify unique words that were properly translated to produce a list of correctly translated words 296. The comparison may also identify unique words that were not properly translated to produce a list of unique words that were not properly translated. Note that each list of words (e.g., specific words and/or phrases, non-words, unique words, translated words and/or phrases, etc.,) may include the word and/or phrase, how many times it is used, where in the data it is used, and/or any other information requested regarding a word and/or phrase.
Continuing with the example of
The task distribution module generates an entry in the task execution information section for each sub-task to be performed. For example, task 1_1 (e.g., identify non-words on the data) has no task ordering (i.e., is independent of the results of other sub-tasks), is to be performed on data partitions 2_1 through 2_z by DT execution modules 1_1, 2_1, 3_1, 4_1, and 5_1. For instance, DT execution modules 1_1, 2_1, 3_1, 4_1, and 5_1 search for non-words in data partitions 2_1 through 2_z to produce task 1_1 intermediate results (R1-1, which is a list of non-words). Task 1_2 (e.g., identify unique words) has similar task execution information as task 1_1 to produce task 1_2 intermediate results (R1-2, which is the list of unique words).
Task 1_3 (e.g., translate) includes task execution information as being non-ordered (i.e., is independent), having DT execution modules 1_1, 2_1, 3_1, 4_1, and 5_1 translate data partitions 2_1 through 2_4 and having DT execution modules 1_2, 2_2, 3_2, 4_2, and 5_2 translate data partitions 2_5 through 2_z to produce task 1_3 intermediate results (R1-3, which is the translated data). In this example, the data partitions are grouped, where different sets of DT execution modules perform a distributed sub-task (or task) on each data partition group, which allows for further parallel processing.
Task 1_4 (e.g., translate back) is ordered after task 1_3 and is to be executed on task 1_3's intermediate result (e.g., R1-3_1) (e.g., the translated data). DT execution modules 1_1, 2_1, 3_1, 4_1, and 5_1 are allocated to translate back task 1_3 intermediate result partitions R1-3_1 through R1-3_4 and DT execution modules 1_2, 2_2, 6_1, 7_1, and 7_2 are allocated to translate back task 1_3 intermediate result partitions R1-3_5 through R1-3_z to produce task 1-4 intermediate results (R1-4, which is the translated back data).
Task 1_5 (e.g., compare data and translated data to identify translation errors) is ordered after task 1_4 and is to be executed on task 1_4's intermediate results (R4-1) and on the data. DT execution modules 1_1, 2_1, 3_1, 4_1, and 5_1 are allocated to compare the data partitions (2_1 through 2_z) with partitions of task 1-4 intermediate results partitions R1-4_1 through R1-4_z to produce task 1_5 intermediate results (R1-5, which is the list words translated incorrectly).
Task 1_6 (e.g., determine non-word translation errors) is ordered after tasks 1_1 and 1_5 and is to be executed on tasks 1_1's and 1_5's intermediate results (R1-1 and R1-5). DT execution modules 1_1, 2_1, 3_1, 4_1, and 5_1 are allocated to compare the partitions of task 1_1 intermediate results (R1-1_1 through R1-1_z) with partitions of task 1-5 intermediate results partitions (R1-5_1 through R1-5_z) to produce task 1_6 intermediate results (R1-6, which is the list translation errors due to non-words).
Task 1_7 (e.g., determine words correctly translated) is ordered after tasks 1_2 and 1_5 and is to be executed on tasks 1_2's and 1_5's intermediate results (R1-1 and R1-5). DT execution modules 1_2, 2_2, 3_2, 4_2, and 5_2 are allocated to compare the partitions of task 1_2 intermediate results (R1-2_1 through R1-2_z) with partitions of task 1-5 intermediate results partitions (R1-5_1 through R1-5_z) to produce task 1_7 intermediate results (R1-7, which is the list of correctly translated words).
Task 2 (e.g., find specific words and/or phrases) has no task ordering (i.e., is independent of the results of other sub-tasks), is to be performed on data partitions 2_1 through 2_z by DT execution modules 3_1, 4_1, 5_1, 6_1, and 7_1. For instance, DT execution modules 3_1, 4_1, 5_1, 6_1, and 7_1 search for specific words and/or phrases in data partitions 2_1 through 2_z to produce task 2 intermediate results (R2, which is a list of specific words and/or phrases).
Task 3_2 (e.g., find specific translated words and/or phrases) is ordered after task 1_3 (e.g., translate) is to be performed on partitions R1-3_1 through R1-3_z by DT execution modules 1_2, 2_2, 3_2, 4_2, and 5_2. For instance, DT execution modules 1_2, 2_2, 3_2, 4_2, and 5_2 search for specific translated words and/or phrases in the partitions of the translated data (R1-3_1 through R1-3_z) to produce task 3_2 intermediate results (R3-2, which is a list of specific translated words and/or phrases).
For each task, the intermediate result information indicates which DST unit is responsible for overseeing execution of the task and, if needed, processing the partial results generated by the set of allocated DT execution units. In addition, the intermediate result information indicates a scratch pad memory for the task and where the corresponding intermediate results are to be stored. For example, for intermediate result R1-1 (the intermediate result of task 1_1), DST unit 1 is responsible for overseeing execution of the task 1_1 and coordinates storage of the intermediate result as encoded intermediate result slices stored in memory of DST execution units 1-5. In general, the scratch pad is for storing non-DS encoded intermediate results and the intermediate result storage is for storing DS encoded intermediate results.
For the first data partition, the first set of DT execution modules (e.g., 1_1, 2_1, 3_1, 4_1, and 5_1 per the DST allocation information of
As indicated in the DST allocation information of
DST execution unit 1 engages its DST client module to slice grouping based DS error encode the first intermediate result (e.g., the list of non-words). To begin the encoding, the DST client module determines whether the list of non-words is of a sufficient size to partition (e.g., greater than a Terabyte). If yes, it partitions the first intermediate result (R1-1) into a plurality of partitions (e.g., R1-1_1 through R1-1_m). If the first intermediate result is not of sufficient size to partition, it is not partitioned.
For each partition of the first intermediate result, or for the first intermediate result, the DST client module uses the DS error encoding parameters of the data (e.g., DS parameters of data 2, which includes 3/5 decode threshold/pillar width ratio) to produce slice groupings. The slice groupings are stored in the intermediate result memory (e.g., allocated memory in the memories of DST execution units 1-5).
In
As indicated in the DST allocation information of
DST execution unit 1 engages its DST client module to slice grouping based DS error encode the second intermediate result (e.g., the list of non-words). To begin the encoding, the DST client module determines whether the list of unique words is of a sufficient size to partition (e.g., greater than a Terabyte). If yes, it partitions the second intermediate result (R1-2) into a plurality of partitions (e.g., R1-2_1 through R1-2_m). If the second intermediate result is not of sufficient size to partition, it is not partitioned.
For each partition of the second intermediate result, or for the second intermediate results, the DST client module uses the DS error encoding parameters of the data (e.g., DS parameters of data 2, which includes 3/5 decode threshold/pillar width ratio) to produce slice groupings. The slice groupings are stored in the intermediate result memory (e.g., allocated memory in the memories of DST execution units 1-5).
In
As indicated in the DST allocation information of
DST execution unit 2 engages its DST client module to slice grouping based DS error encode the third intermediate result (e.g., translated data). To begin the encoding, the DST client module partitions the third intermediate result (R1-3) into a plurality of partitions (e.g., R1-3_1 through R1-3_y). For each partition of the third intermediate result, the DST client module uses the DS error encoding parameters of the data (e.g., DS parameters of data 2, which includes 3/5 decode threshold/pillar width ratio) to produce slice groupings. The slice groupings are stored in the intermediate result memory (e.g., allocated memory in the memories of DST execution units 2-6 per the DST allocation information).
As is further shown in
As indicated in the DST allocation information of
DST execution unit 3 engages its DST client module to slice grouping based DS error encode the fourth intermediate result (e.g., retranslated data). To begin the encoding, the DST client module partitions the fourth intermediate result (R1-4) into a plurality of partitions (e.g., R1-4_1 through R1-4_z). For each partition of the fourth intermediate result, the DST client module uses the DS error encoding parameters of the data (e.g., DS parameters of data 2, which includes 3/5 decode threshold/pillar width ratio) to produce slice groupings. The slice groupings are stored in the intermediate result memory (e.g., allocated memory in the memories of DST execution units 3-7 per the DST allocation information).
In
For each pair of partitions (e.g., data partition 1 and retranslated data partition 1), the DSTN identifies a set of its DT execution modules 90 to perform task 1_5 in accordance with the DST allocation information (e.g., DT execution modules 1_1, 2_1, 3_1, 4_1, and 5_1). For each pair of partitions, the allocated set of DT execution modules executes task 1_5 to produce partial results 102 (e.g., 1st through “zth”) of a list of incorrectly translated words and/or phrases.
As indicated in the DST allocation information of
DST execution unit 1 engages its DST client module to slice grouping based DS error encode the fifth intermediate result. To begin the encoding, the DST client module partitions the fifth intermediate result (R1-5) into a plurality of partitions (e.g., R1-5_1 through R1-5_z). For each partition of the fifth intermediate result, the DST client module uses the DS error encoding parameters of the data (e.g., DS parameters of data 2, which includes 3/5 decode threshold/pillar width ratio) to produce slice groupings. The slice groupings are stored in the intermediate result memory (e.g., allocated memory in the memories of DST execution units 1-5 per the DST allocation information).
As is further shown in
For each pair of partitions (e.g., partition R1-1_1 and partition R1-5_1), the DSTN identifies a set of its DT execution modules 90 to perform task 1_6 in accordance with the DST allocation information (e.g., DT execution modules 1_1, 2_1, 3_1, 4_1, and 5_1). For each pair of partitions, the allocated set of DT execution modules executes task 1_6 to produce partial results 102 (e.g., 1st through “zth”) of a list of incorrectly translated words and/or phrases due to non-words.
As indicated in the DST allocation information of
DST execution unit 2 engages its DST client module to slice grouping based DS error encode the sixth intermediate result. To begin the encoding, the DST client module partitions the sixth intermediate result (R1-6) into a plurality of partitions (e.g., R1-6_1 through R1-6_z). For each partition of the sixth intermediate result, the DST client module uses the DS error encoding parameters of the data (e.g., DS parameters of data 2, which includes 3/5 decode threshold/pillar width ratio) to produce slice groupings. The slice groupings are stored in the intermediate result memory (e.g., allocated memory in the memories of DST execution units 2-6 per the DST allocation information).
As is still further shown in
For each pair of partitions (e.g., partition R1-2_1 and partition R1-5_1), the DSTN identifies a set of its DT execution modules 90 to perform task 1_7 in accordance with the DST allocation information (e.g., DT execution modules 1_2, 2_2, 3_2, 4_2, and 5_2). For each pair of partitions, the allocated set of DT execution modules executes task 1_7 to produce partial results 102 (e.g., 1st through “zth”) of a list of correctly translated words and/or phrases.
As indicated in the DST allocation information of
DST execution unit 3 engages its DST client module to slice grouping based DS error encode the seventh intermediate result. To begin the encoding, the DST client module partitions the seventh intermediate result (R1-7) into a plurality of partitions (e.g., R1-7_1 through R1-7_z). For each partition of the seventh intermediate result, the DST client module uses the DS error encoding parameters of the data (e.g., DS parameters of data 2, which includes 3/5 decode threshold/pillar width ratio) to produce slice groupings. The slice groupings are stored in the intermediate result memory (e.g., allocated memory in the memories of DST execution units 3-7 per the DST allocation information).
In
As indicated in the DST allocation information of
DST execution unit 7 engages its DST client module to slice grouping based DS error encode the task 2 intermediate result. To begin the encoding, the DST client module determines whether the list of specific words and/or phrases is of a sufficient size to partition (e.g., greater than a Terabyte). If yes, it partitions the task 2 intermediate result (R2) into a plurality of partitions (e.g., R2_1 through R2_m). If the task 2 intermediate result is not of sufficient size to partition, it is not partitioned.
For each partition of the task 2 intermediate result, or for the task 2 intermediate results, the DST client module uses the DS error encoding parameters of the data (e.g., DS parameters of data 2, which includes 3/5 decode threshold/pillar width ratio) to produce slice groupings. The slice groupings are stored in the intermediate result memory (e.g., allocated memory in the memories of DST execution units 1-4, and 7).
In
As indicated in the DST allocation information of
DST execution unit 5 engages its DST client module to slice grouping based DS error encode the task 3 intermediate result. To begin the encoding, the DST client module determines whether the list of specific translated words and/or phrases is of a sufficient size to partition (e.g., greater than a Terabyte). If yes, it partitions the task 3 intermediate result (R3) into a plurality of partitions (e.g., R3_1 through R3_m). If the task 3 intermediate result is not of sufficient size to partition, it is not partitioned.
For each partition of the task 3 intermediate result, or for the task 3 intermediate results, the DST client module uses the DS error encoding parameters of the data (e.g., DS parameters of data 2, which includes 3/5 decode threshold/pillar width ratio) to produce slice groupings. The slice groupings are stored in the intermediate result memory (e.g., allocated memory in the memories of DST execution units 1-4, 5, and 7).
The decentralized agreement module 350 functions to receive a ranked scoring information request 354 and to generate ranked scoring information 358 based on the ranked scoring information request 354 and other information. The ranked scoring information request 354 includes one or more of an asset identifier (ID) 356 of an asset associated with the request, an asset type indicator, one or more location identifiers of locations associated with the DSN, one or more corresponding location weights, and a requesting entity ID. The asset includes any portion of data associated with the DSN including one or more asset types including a data object, a data record, an encoded data slice, a data segment, a set of encoded data slices, and a plurality of sets of encoded data slices. As such, the asset ID 356 of the asset includes one or more of a data name, a data record identifier, a source name, a slice name, and a plurality of sets of slice names.
Each location of the DSN includes an aspect of a DSN resource. Examples of locations includes one or more of a storage unit, a memory device of the storage unit, a site, a storage pool of storage units, a pillar index associated with each encoded data slice of a set of encoded data slices generated by an information dispersal algorithm (IDA), a DST client module 34 of FIG. 1, a DST processing unit 16 of
Each location is associated with a location weight based on one or more of a resource prioritization of utilization scheme and physical configuration of the DSN. The location weight includes an arbitrary bias which adjusts a proportion of selections to an associated location such that a probability that an asset will be mapped to that location is equal to the location weight divided by a sum of all location weights for all locations of comparison. For example, each storage pool of a plurality of storage pools is associated with a location weight based on storage capacity. For instance, storage pools with more storage capacity are associated with higher location weights than others. The other information may include a set of location identifiers and a set of location weights associated with the set of location identifiers. For example, the other information includes location identifiers and location weights associated with a set of memory devices of a storage unit when the requesting entity utilizes the decentralized agreement module 350 to produce ranked scoring information 358 with regards to selection of a memory device of the set of memory devices for accessing a particular encoded data slice (e.g., where the asset ID includes a slice name of the particular encoded data slice).
The decentralized agreement module 350 outputs substantially identical ranked scoring information for each ranked scoring information request that includes substantially identical content of the ranked scoring information request. For example, a first requesting entity issues a first ranked scoring information request to the decentralized agreement module 350 and receives first ranked scoring information. A second requesting entity issues a second ranked scoring information request to the decentralized agreement module and receives second ranked scoring information. The second ranked scoring information is substantially the same as the first ranked scoring information when the second ranked scoring information request is substantially the same as the first ranked scoring information request.
As such, two or more requesting entities may utilize the decentralized agreement module 350 to determine substantially identical ranked scoring information. As a specific example, the first requesting entity selects a first storage pool of a plurality of storage pools for storing a set of encoded data slices utilizing the decentralized agreement module 350 and the second requesting entity identifies the first storage pool of the plurality of storage pools for retrieving the set of encoded data slices utilizing the decentralized agreement module 350.
In an example of operation, the decentralized agreement module 350 receives the ranked scoring information request 354. Each deterministic function performs a deterministic function on a combination and/or concatenation (e.g., add, append, interleave) of the asset ID 356 of the ranked scoring information request 354 and an associated location ID of the set of location IDs to produce an interim result. The deterministic function includes at least one of a hashing function, a hash-based message authentication code function, a mask generating function, a cyclic redundancy code function, hashing module of a number of locations, consistent hashing, rendezvous hashing, and a sponge function. As a specific example, deterministic function 2 appends a location ID 2 of a storage pool 2 to a source name as the asset ID to produce a combined value and performs the mask generating function on the combined value to produce interim result 2.
With a set of interim results 1-N, each normalizing function performs a normalizing function on a corresponding interim result to produce a corresponding normalized interim result. The performing of the normalizing function includes dividing the interim result by a number of possible permutations of the output of the deterministic function to produce the normalized interim result. For example, normalizing function 2 performs the normalizing function on the interim result 2 to produce a normalized interim result 2.
With a set of normalized interim results 1-N, each scoring function performs a scoring function on a corresponding normalized interim result to produce a corresponding score. The performing of the scoring function includes dividing an associated location weight by a negative log of the normalized interim result. For example, scoring function 2 divides location weight 2 of the storage pool 2 (e.g., associated with location ID 2) by a negative log of the normalized interim result 2 to produce a score 2.
With a set of scores 1-N, the ranking function 352 performs a ranking function on the set of scores 1-N to generate the ranked scoring information 358. The ranking function includes rank ordering each score with other scores of the set of scores 1-N, where a highest score is ranked first. As such, a location associated with the highest score may be considered a highest priority location for resource utilization (e.g., accessing, storing, retrieving, etc., the given asset of the request). Having generated the ranked scoring information 358, the decentralized agreement module 350 outputs the ranked scoring information 358 to the requesting entity.
For each interim result, the method continues at step 364 where the processing module performs a normalizing function on the interim result to produce a normalized interim result. As a specific example, the processing module obtains a permutation value associated with the deterministic function (e.g., maximum number of permutations of output of the deterministic function) and divides the interim result by the permutation value to produce the normalized interim result (e.g., with a value between 0 and 1).
For each normalized interim result, the method continues at step 366 where the processing module performs a scoring function on the normalized interim result utilizing a location weight associated with the candidate resource associated with the interim result to produce a score of a set of scores. As a specific example, the processing module divides the location weight by a negative log of the normalized interim result to produce the score.
The method continues at step 368 where the processing module rank orders the set of scores to produce ranked scoring information (e.g., ranking a highest value first). The method continues at step 370 where the processing module outputs the ranked scoring information to the requesting entity. The requesting entity may utilize the ranked scoring information to select one location of a plurality of locations.
The DSN functions to receive data access requests 382, select resources of at least one DST execution unit pool for data access, utilize the selected DST execution unit pool for the data access, and issue a data access response 392 based on the data access. The selecting of the resources includes utilizing a decentralized agreement function of the decentralized agreement module 380, where a plurality of locations are ranked against each other. The selecting may include selecting one storage pool of the plurality of storage pools, selecting DST execution units at various sites of the plurality of sites, selecting a memory of the plurality of memories for each DST execution unit, and selecting combinations of memories, DST execution units, sites, pillars, and storage pools.
In an example of operation, the DST client module 34 receives the data access request 382 from a requesting entity, where the data access request 382 includes at least one of a store data request, a retrieve data request, a delete data request, a data name, and a requesting entity identifier (ID). Having received the data access request 382, the DST client module 34 determines a DSN address associated with the data access request. The DSN address includes at least one of a source name (e.g., including a vault ID and an object number associated with the data name), a data segment ID, a set of slice names, a plurality of sets of slice names. The determining includes at least one of generating (e.g., for the store data request) and retrieving (e.g., from a DSN directory, from a dispersed hierarchical index) based on the data name (e.g., for the retrieve data request).
Having determined the DSN address, the DST client module 34 selects a plurality of resource levels (e.g., DST EX unit pool, site, DST execution unit, pillar, memory) associated with the DSTN module 22. The determining may be based on one or more of the data name, the requesting entity ID, a predetermination, a lookup, a DSN performance indicator, and interpreting an error message. For example, the DST client module 34 selects the DST execution unit pool as a first resource level and a set of memory devices of a plurality of memory devices as a second resource level based on a system registry lookup for a vault associated with the requesting entity.
Having selected the plurality of resource levels, the DST client module 34, for each resource level, issues a ranked scoring information request 384 to the decentralized agreement module 380 utilizing the DSN address as an asset ID. The decentralized agreement module 380 performs the decentralized agreement function based on the asset ID (e.g., the DSN address), identifiers of locations of the selected resource levels, and location weights of the locations to generate ranked scoring information 386.
For each resource level, the DST client module 34 receives corresponding ranked scoring information 386. Having received the ranked scoring information 386, the DST client module 34 identifies one or more resources associated with the resource level based on the rank scoring information 386. For example, the DST client module 34 identifies a DST execution unit pool associated with a highest score and identifies a set of memory devices within DST execution units of the identified DST execution unit pool with a highest score.
Having identified the one or more resources, the DST client module 34 accesses the DSTN module 22 based on the identified one or more resources associated with each resource level. For example, the DST client module 34 issues resource access requests 388 (e.g., write slice requests when storing data, read slice requests when recovering data) to the identified DST execution unit pool, where the resource access requests 388 further identify the identified set of memory devices. Having accessed the DSTN module 22, the DST client module 34 receives resource access responses 390 (e.g., write slice responses, read slice responses). The DST client module 34 issues the data access response 392 based on the received resource access responses 390. For example, the DST client module 34 decodes received encoded data slices to reproduce data and generates the data access response 392 to include the reproduced data.
The method continues at step 398 where the processing module selects a plurality of resource levels associated with the DSN memory. The selecting may be based on one or more of a predetermination, a range of weights associated with available resources, a resource performance level, and a resource performance requirement level. For each resource level, the method continues at step 400 where the processing module determines ranked scoring information. For example, the processing module issues a ranked scoring information request to a decentralized agreement module based on the DSN address and receives corresponding ranked scoring information for the resource level, where the decentralized agreement module performs a decentralized agreement protocol function on the DSN address using the associated resource identifiers and resource weights for the resource level to produce the ranked scoring information for the resource level.
For each resource level, the method continues at step 402 where the processing module selects one or more resources associated with the resource level based on the ranked scoring information. For example, the processing module selects a resource associated with a highest score when one resource is required. As another example, the processing module selects a plurality of resources associated with highest scores when a plurality of resources are required.
The method continues at step 404 where the processing module accesses the DSN memory utilizing the selected one or more resources for each of the plurality of resource levels. For example, the processing module identifies network addressing information based on the selected resources including one or more of a storage unit Internet protocol address and a memory device identifier, generates a set of encoded data slice access requests based on the data access request and the DSN address, and sends the set of encoded data slice access requests to the DSN memory utilizing the identified network addressing information.
The method continues at step 406 where the processing module issues a data access response to the requesting entity based on one or more resource access responses from the DSN memory. For example, the processing module issues a data storage status indicator when storing data. As another example, the processing module generates the data access response to include recovered data when retrieving data.
In various embodiments, a global coordination unit sets a schedule for when each manager device included in a DSN is permitted to initiate connections with the coordination unit. The schedule can be set by taking into account the known, configured timezone of each connecting manager, and returning a calculated schedule. The timezone and schedule can be passed as part of a communications protocol followed by members of the DSN. For example, a scheduling module can attempt to evenly distribute client connections across a given time period X, starting from a given hour Y, on a periodic basis (e.g. daily). In some embodiments, the scheduling module determines the total number of clients in each timezone, and beginning with hour Y, each managing unit of each DSN memory or other distributed computing system can be assigned the time Y+X(N−1) where N is the Nth client in that timezone. For example, the first client in GMT is assigned to start the connection every day at Y. The second client is assigned Y+X1, 3rd is assigned Y+X2, etc. This process can be repeated for each timezone containing at least one manager device.
In some embodiments, a maximum number N of processing devices may be configured before N exceeds a threshold value, and when that threshold value is exceeded, the length of the time period assigned to each managing unit can be modified. For example, if X is normally one minute, but more than 60 managers are in that time zone such that the collection times would span an hour, then the period may be reduced to an amount that keeps all collections within that hour. In this way, some embodiments can globally control when individual DSN memories and other distributed computing systems that make up a dispersed storage network initiate connections.
In an example of operation of the assigning of the timing of the coordinating of the plurality of distributed computing systems, for each time zone of a plurality of global time zones, the scheduling module 421 identifies a number of distributed computing systems for coordination of scheduling. The determining includes one or more of interpreting system registry information, interpreting a query response, and interpreting a request. Having identified the number of distributed computing systems, the scheduling module, for each time zone, selects a connection time assignment approach to enable assignment of a unique connection times to each of the number of the distributed computing systems within the time zone. The assignment approaches includes an even distribution, a distribution every “X” seconds, frontloaded distribution, backloaded distribution, random distribution, parallel distribution, etc. The selecting of the connection time assignment approach may be based on one or more of system registry information, a request, a predetermination, the number of distributed computing systems and/or DSN memories associated with the time zone, and a network loading level.
Having selected the connection time approach, for each time zone, the scheduling module assigns the unique connection time to each of the number of distributed computing systems and/or DSN memories, where a total number of unique connection times are assigned within a span of the time zone (e.g., 30 minutes, one hour, two hours, etc.). The assigning includes applying the selected assignment approach to produce the total number of unique connection times. For example, the scheduling module utilizes a formula of unique assignment (N)=Y+X(N−1) where N is the Nth client in that time zone and Y represents a starting time. For instance, a first system in GMT is assigned to start its connection every day at Y. A second system is assigned Y+X1, 3rd is assigned Y+X2, etc. As another example, the scheduling module assigns a maximum of N that may be configured such that when it is exceeded that period is modified. For instance, if X is normally one minute, but more than 60 managing units are in that time zone such that the collection times would span an hour of the time zone, then the period may be reduced to an amount that keeps all collections within that hour. As a specific example, for the first 60 systems, the schedules range from 2:00:00 to 2:59:00 in one minute increments—i.e. 2:00, 2:01, . . . 2:59. For systems 60-120, the schedules range from 2:00:30 to 2:59:30 in one minute increments—i.e. 2:00:30, 2:01:30, . . . 2:59:30. For systems 120-240, the schedules range from 2:00:15 to 2:59:45 in 30 second increments—i.e. 2:00:15, 2:00:45, 2:01:15, 2:01:45, . . . 2:59:15, 2:59:45.
Having assigned the unique connection times, scheduling module 421 issues, via the network 24, scheduling messages 412, 414, 416, and 418 to each distributed computing system, where the scheduling messages includes, for each time zone, the assigned unique connection time for each of the distributed computing systems/DSN memories. For each distributed computing system receiving a corresponding scheduling message, the appropriate DSTN managing unit 18 initiates establishment of a connection to the coordination unit in accordance with the received assigned unique connection time to facilitate coordination activities.
For each time zone, the method continues at block 434, where the processing module selects a connection time assignment approach to enable assignment of a unique connection time to each of the number of the distributed computing systems associated with the time zone. The selecting may be based on one or more of system registry information, a request, a predetermination, the number of distributed computing systems associated with the time zone, and a network loading level.
For each time zone, the method continues at block 436, where the processing module assigns the unique connection time to each of the number of distributed computing systems, where a total number of unique connection times are assigned within a time span of the time zone. The assigning includes applying the selected assignment approach to produce the total number of unique connection times.
The method continues at block 438 where the processing module issues scheduling messages to each distributed computing system. The issuing includes generating the scheduling message to include the assignment of the unique connection time for the distributed computing system and sending the scheduling message to the corresponding distributed computing system.
The method continues at block 440, where each distributed computing system initiates establishment of a connection to a coordination unit in accordance with the assigned unique connection time to facilitate coordination activities. For example, the distributed computing system and/or DSN memory determines when to initiate/establish the connection to the coordination unit based on the assigned unique connection time and establishes the connection at the determined time frame.
As may be used herein, the terms “substantially” and “approximately” provides an industry-accepted tolerance for its corresponding term and/or relativity between items. Such an industry-accepted tolerance ranges from less than one percent to fifty percent and corresponds to, but is not limited to, component values, integrated circuit process variations, temperature variations, rise and fall times, and/or thermal noise. Such relativity between items ranges from a difference of a few percent to magnitude differences. As may also be used herein, the term(s) “operably coupled to”, “coupled to”, and/or “coupling” includes direct coupling between items and/or indirect coupling between items via an intervening item (e.g., an item includes, but is not limited to, a component, an element, a circuit, and/or a module) where, for indirect coupling, the intervening item does not modify the information of a signal but may adjust its current level, voltage level, and/or power level. As may further be used herein, inferred coupling (i.e., where one element is coupled to another element by inference) includes direct and indirect coupling between two items in the same manner as “coupled to”. As may even further be used herein, the term “operable to” or “operably coupled to” indicates that an item includes one or more of power connections, input(s), output(s), etc., to perform, when activated, one or more its corresponding functions and may further include inferred coupling to one or more other items. As may still further be used herein, the term “associated with”, includes direct and/or indirect coupling of separate items and/or one item being embedded within another item. As may be used herein, the term “compares favorably”, indicates that a comparison between two or more items, signals, etc., provides a desired relationship. For example, when the desired relationship is that signal 1 has a greater magnitude than signal 2, a favorable comparison may be achieved when the magnitude of signal 1 is greater than that of signal 2 or when the magnitude of signal 2 is less than that of signal 1.
As may also be used herein, the terms “processing module”, “processing circuit”, and/or “processing unit” may be a single processing device or a plurality of processing devices. Such a processing device may be a microprocessor, micro-controller, digital signal processor, microcomputer, central processing unit, field programmable gate array, programmable logic device, state machine, logic circuitry, analog circuitry, digital circuitry, and/or any device that manipulates signals (analog and/or digital) based on hard coding of the circuitry and/or operational instructions. The processing module, module, processing circuit, and/or processing unit may be, or further include, memory and/or an integrated memory element, which may be a single memory device, a plurality of memory devices, and/or embedded circuitry of another processing module, module, processing circuit, and/or processing unit. Such a memory device may be a read-only memory, random access memory, volatile memory, non-volatile memory, static memory, dynamic memory, flash memory, cache memory, and/or any device that stores digital information. Note that if the processing module, module, processing circuit, and/or processing unit includes more than one processing device, the processing devices may be centrally located (e.g., directly coupled together via a wired and/or wireless bus structure) or may be distributedly located (e.g., cloud computing via indirect coupling via a local area network and/or a wide area network). Further note that if the processing module, module, processing circuit, and/or processing unit implements one or more of its functions via a state machine, analog circuitry, digital circuitry, and/or logic circuitry, the memory and/or memory element storing the corresponding operational instructions may be embedded within, or external to, the circuitry comprising the state machine, analog circuitry, digital circuitry, and/or logic circuitry. Still further note that, the memory element may store, and the processing module, module, processing circuit, and/or processing unit executes, hard coded and/or operational instructions corresponding to at least some of the steps and/or functions illustrated in one or more of the Figures. Such a memory device or memory element can be included in an article of manufacture.
The present invention has been described above with the aid of method steps illustrating the performance of specified functions and relationships thereof. The boundaries and sequence of these functional building blocks and method steps have been arbitrarily defined herein for convenience of description. Alternate boundaries and sequences can be defined so long as the specified functions and relationships are appropriately performed. Any such alternate boundaries or sequences are thus within the scope and spirit of the claimed invention. Further, the boundaries of these functional building blocks have been arbitrarily defined for convenience of description. Alternate boundaries could be defined as long as the certain significant functions are appropriately performed. Similarly, flow diagram blocks may also have been arbitrarily defined herein to illustrate certain significant functionality. To the extent used, the flow diagram block boundaries and sequence could have been defined otherwise and still perform the certain significant functionality. Such alternate definitions of both functional building blocks and flow diagram blocks and sequences are thus within the scope and spirit of the claimed invention. One of average skill in the art will also recognize that the functional building blocks, and other illustrative blocks, modules and components herein, can be implemented as illustrated or by discrete components, application specific integrated circuits, processors executing appropriate software and the like or any combination thereof.
The present invention may have also been described, at least in part, in terms of one or more embodiments. An embodiment of the present invention is used herein to illustrate the present invention, an aspect thereof, a feature thereof, a concept thereof, and/or an example thereof. A physical embodiment of an apparatus, an article of manufacture, a machine, and/or of a process that embodies the present invention may include one or more of the aspects, features, concepts, examples, etc., described with reference to one or more of the embodiments discussed herein. Further, from figure to figure, the embodiments may incorporate the same or similarly named functions, steps, modules, etc., that may use the same or different reference numbers and, as such, the functions, steps, modules, etc., may be the same or similar functions, steps, modules, etc., or different ones.
While the transistors in the above described figure(s) is/are shown as field effect transistors (FETs), as one of ordinary skill in the art will appreciate, the transistors may be implemented using any type of transistor structure including, but not limited to, bipolar, metal oxide semiconductor field effect transistors (MOSFET), N-well transistors, P-well transistors, enhancement mode, depletion mode, and zero voltage threshold (VT) transistors.
Unless specifically stated to the contra, signals to, from, and/or between elements in a figure of any of the figures presented herein may be analog or digital, continuous time or discrete time, and single-ended or differential. For instance, if a signal path is shown as a single-ended path, it also represents a differential signal path. Similarly, if a signal path is shown as a differential path, it also represents a single-ended signal path. While one or more particular architectures are described herein, other architectures can likewise be implemented that use one or more data buses not expressly shown, direct connectivity between elements, and/or indirect coupling between other elements as recognized by one of average skill in the art.
The term “module” is used in the description of the various embodiments of the present invention. A module includes a processing module, a functional block, hardware, and/or software stored on memory for performing one or more functions as may be described herein. Note that, if the module is implemented via hardware, the hardware may operate independently and/or in conjunction software and/or firmware. As used herein, a module may contain one or more sub-modules, each of which may be one or more modules.
While particular combinations of various functions and features of the present invention have been expressly described herein, other combinations of these features and functions are likewise possible. The present invention is not limited by the particular examples disclosed herein and expressly incorporates these other combinations.
Claims
1. A method for use in a dispersed storage network (DSN) including a plurality of distributed computing systems, each computing system including a DSN memory, the method comprising:
- identifying, at a coordination unit used by the plurality of distributed computing systems, a subset of distributed computing systems, the subset of distributed computing systems including a number of distributed computing systems;
- selecting, by the coordination unit, connection times for the subset of distributed computing systems, wherein: the connection times are selected, at least in part, based on the number of distributed computing systems included in the subset of distributed computing systems, and a connection time selected for a particular distributed computing system specifies a recurring time period to be used by the particular distributed computing system for initiating a connection with the coordination unit; and
- issuing scheduling messages, from the coordination unit to the subset of distributed computing systems, wherein the scheduling messages include information specifying connection times selected for individual distributed computing systems.
2. The method of claim 1, wherein selecting the connection times includes:
- selecting a connection-time assignment approach from among a plurality of different connection-time assignment approaches.
3. The method of claim 2, wherein the connection-time assignment approach is selected from the group consisting of: even distribution, every “X” seconds, frontloaded distribution, backloaded distribution, random distribution, and parallel distribution.
4. The method of claim 1, wherein selecting the connection times includes:
- attempting to evenly distribute connection times across a given period of time, the given period of time repeated on a periodic basis.
5. The method of claim 4, wherein:
- the given period of time is a portion of an hour;
- the given period of time begins at a given hour; and
- the given period of time repeats at least on a daily basis.
6. The method of claim 1, wherein selecting the connection times includes:
- modifying a length of the recurring time period in response to determining that the number of distributed computing systems included in the subset of distributed computing systems exceeds a threshold value.
7. The method of claim 1, wherein selecting the connection times includes:
- modifying a length of the recurring time period to limit all recurring time periods assigned to distributed computing systems within the subset of distributed computing systems to occur within a given length of time, wherein a period of recurrence corresponds to the given length of time.
8. A processing system configured to implement a coordination unit for use in a distributed storage network (DSN) including a plurality of distributed computing systems, the coordination unit comprising:
- at least one computing core and associated memory configured to implement a scheduling module coupled to the plurality of distributed computing systems included in the DSN;
- the scheduling module configured to: identify a subset of distributed computing systems, the subset of distributed computing systems including a number of distributed computing systems; select connection times for the subset of distributed computing systems, wherein: the connection times are selected, at least in part, based on the number of distributed computing systems included in the subset of distributed computing systems, and a connection time selected for a particular distributed computing system specifies a recurring time period to be used by the particular distributed computing system for initiating a connection with the coordination unit; and issue scheduling messages to the subset of distributed computing systems, wherein the scheduling messages include information specifying connection times selected for individual distributed computing systems.
9. The processing system of claim 8, wherein the scheduling module is further configured to:
- select a connection-time assignment approach from among a plurality of different connection-time assignment approaches.
10. The processing system of claim 9, wherein the scheduling module is further configured to:
- select the connection-time assignment approach from the group consisting of: every “X” seconds, frontloaded distribution, backloaded distribution, random distribution, and parallel distribution.
11. The processing system of claim 8, wherein the scheduling module is further configured to:
- attempt to evenly distribute connection times across a given period of time, the given period of time repeated on a periodic basis.
12. The processing system of claim 11, wherein:
- the given period of time is a portion of an hour;
- the given period of time begins at a given hour; and
- the given period of time repeats at least on a daily basis.
13. The processing system of claim 8, wherein the scheduling module is further configured to:
- modify a length of the recurring time period in response to determining that the number of distributed computing systems included in the subset of distributed computing systems exceeds a threshold value.
14. The processing system of claim 13, wherein the scheduling module is further configured to:
- select the length of the recurring time period to limit all recurring time periods assigned to distributed computing systems within the subset of distributed computing systems to occur within a given length of time, wherein a period of recurrence corresponds to the given length of time.
15. A distributed storage network (DSN), the DSN comprising:
- a plurality distributed computing systems implementing a plurality of DSN memories, each of the plurality of DSN memories including a DSTN managing unit;
- a coordination unit coupled to the DSTN managing unit included in each of the plurality of DSN memories, the coordination unit including at least one computing core and associated memory configured to implement a scheduling module;
- the scheduling module configured to: identify a subset of distributed computing systems, the subset of distributed computing systems including a number of distributed computing systems; select connection times for the subset of distributed computing systems, wherein: the connection times are selected, at least in part, based on the number of distributed computing systems included in the subset of distributed computing systems, and a connection time selected for a particular distributed computing system specifies a recurring time period to be used by the particular distributed computing system for initiating a connection with the coordination unit; and issue scheduling messages to the subset of distributed computing systems, wherein the scheduling messages include information specifying connection times selected for individual distributed computing systems.
16. The distributed storage network of claim 15, wherein the scheduling module is further configured to:
- select a connection-time assignment approach from among a plurality of different connection-time assignment approaches.
17. The distributed storage network of claim 16, wherein the scheduling module is further configured to:
- select the connection-time assignment approach from the group consisting of: every “X” seconds, frontloaded distribution, backloaded distribution, random distribution, and parallel distribution.
18. The distributed storage network of claim 15, wherein the scheduling module is further configured to:
- attempt to evenly distribute connection times across a given period of time, the given period of time repeated on a periodic basis.
19. The distributed storage network of claim 15, wherein the scheduling module is further configured to:
- modify a length of the recurring time period in response to determining that the number of distributed computing systems included in the subset of distributed computing systems exceeds a threshold value.
20. The distributed storage network of claim 15, wherein the scheduling module is further configured to:
- select a length of the recurring time period to limit all recurring time periods assigned to distributed computing systems within the subset of distributed computing systems to occur within a given length of time, wherein a period of recurrence corresponds to the given length of time.
Type: Application
Filed: Nov 9, 2018
Publication Date: Mar 28, 2019
Patent Grant number: 10606507
Inventors: Charles H. Chong (Chicago, IL), Richard W. France (Schaumburg, IL), Patrick A. Tamborski (Chicago, IL)
Application Number: 16/185,738
